NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
By: Brent Zoomers , Florian Hahlbohm , Joni Vanherck and more
Potential Business Impact:
Makes 3D scenes draw much faster.
3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling. We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer. Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques.
Similar Papers
VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
CV and Pattern Recognition
Makes 3D pictures look real from any angle.
Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittance
CV and Pattern Recognition
Renders see-through objects perfectly, no matter how they overlap.
EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
CV and Pattern Recognition
Creates realistic 3D scenes from many pictures.